JP2016201084A - Image processor and computer readable storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor capable of quantitatively determining the clearness in a binary image area and a computer readable storage medium.SOLUTION: An image processor in an embodiment includes: a calculation unit; a comparison determination unit; and an output unit. The calculation unit calculates a standard deviation and an entropy based on a piece of tone information of a pixel constituting an image and calculates the ratio between the standard deviation and the entropy. The comparison determination unit compares the ratio and the reference value. The output unit outputs a comparison result by the comparison determination unit.SELECTED DRAWING: Figure 8

Description

  Embodiments described herein relate generally to an image processing apparatus and a computer-readable storage medium.

  Warehouse and store managers manage many items on the shelves. Such management is performed by a device that takes a picture of an article and identifies a character string described on a label attached to the article shown in the image. The character string portion in the image is a binary image area. The binary image area of the image must be clear enough for the device to identify the character string. Therefore, a technique capable of quantitatively determining the sharpness of the binary image region is desired.

Japanese Patent No. 4412214

  The problem to be solved by the embodiments of the present invention is to provide an image processing apparatus and a computer-readable storage medium capable of quantitatively determining the sharpness of a binary image area.

  According to the embodiment, the image processing apparatus includes a calculation unit, a comparison determination unit, and an output unit. The arithmetic unit calculates a standard deviation and entropy based on gradation information of pixels constituting the image, and calculates a ratio between the standard deviation and the entropy. The comparison determination unit compares the ratio with a reference value. The output unit outputs a comparison result by the comparison determination unit.

1 is a block diagram of an example image processing apparatus according to a first embodiment. FIG. FIG. 3 is a diagram illustrating a moving direction of an image processing apparatus as an example according to the first embodiment. The figure for demonstrating the parameter | index used as an example used for the sharpness determination which concerns on 1st Embodiment. The figure which shows the value of SER calculated by the image processing apparatus which concerns on 1st Embodiment. 6 is a flowchart of an example process performed by the image processing apparatus according to the first embodiment. 9 is a flowchart of another example process performed by the image processing apparatus according to the first embodiment. The figure which shows the image used as a comparative example. FIG. 6 is a diagram for explaining a sharpness determination method by an image processing apparatus according to a second embodiment. 10 is a flowchart of an example process performed by the image processing apparatus according to the second embodiment. 10 is a flowchart of another example process performed by the image processing apparatus according to the second embodiment. FIG. 10 is a block diagram of an image processing apparatus as an example according to a third embodiment.

Several embodiments will be described below with reference to the drawings.
(First embodiment)
A first embodiment will be described. FIG. 1 is a block diagram of an image processing apparatus 10 as an example according to the first embodiment.
The image processing apparatus 10 is used for inventory management of a plurality of articles placed on a shelf 20 in a warehouse or store. The image processing apparatus 10 includes a moving body 11, a control unit 12, a photographing unit 13, a processing unit 14, a storage unit 15, a display unit 16, and an audio output unit 17. Note that the image processing apparatus 10 does not necessarily include all these elements. For example, the image processing apparatus 10 may be an apparatus including at least the processing unit 14 and the storage unit 15.

  The moving body 11 is a cart that can move the image processing apparatus 10 in any direction. The movable body 11 can travel in a direction parallel to the extending direction of the shelves 20 arranged in a straight line, or can travel in a direction orthogonal to the extending direction of the shelves 20.

  The control unit 12 controls the operation of the moving body 11 based on the signal from the processing unit 14. The control unit 12 controls the traveling direction of the moving body 11 and the start and stop of traveling. The operation of the moving body 11 may be determined by the processing unit 14 or the control unit 12.

  The photographing unit 13 is a camera that includes a lens 131 and photographs an image. The imaging unit 13 may be a camera that captures moving images or a camera that captures still images. The imaging unit 13 sends the captured image data to the processing unit 14.

  The processing unit 14 corresponds to a central part of the image processing apparatus 10. The processing unit 14 controls each element of the image processing apparatus 10 according to an operating system and application programs. The processing unit 14 includes a calculation unit 141 and a comparison determination unit 142. The processing unit 14 quantitatively determines the sharpness of the binary image region included in one image captured by the imaging unit 13 by the calculation unit 141 and the comparison determination unit 142. The binary image area is an area where, for example, characters and symbols in the image are captured. The sharpness of the binary image area corresponds to the ease of recognizing the binary image area or the degree of defocus in the binary image area. A technique for quantitatively determining the sharpness of the binary image area included in one image (hereinafter referred to as “sharpness determination”) will be described later.

  The processing unit 14 sends an operation instruction of the moving body 11 to the control unit 12. The processing unit 14 may send the result of the sharpness determination by the processing unit 14 to the control unit 12. In this case, the control unit 12 determines the operation of the moving body 11 based on the sharpness determination.

  The processing unit 14 sends a signal related to display on the display unit 16 to the display unit 16. The processing unit 14 sends a signal related to the audio output from the audio output unit 17 to the audio output unit 17.

  The storage unit 15 includes a memory that stores the operating system and application programs. Furthermore, the storage unit 15 includes a memory serving as a work area necessary for processing by the processing unit 14. Furthermore, the storage unit 15 includes a memory that stores data necessary for processing by the processing unit 14. The storage unit 15 stores a plurality of reference values 151. The plurality of reference values 151 are threshold values for determining the sharpness.

  The display unit 16 is a display that displays an image based on a signal from the processing unit 14. The audio output unit 17 is a speaker that outputs audio based on a signal from the processing unit 14. The display unit 16 and the audio output unit 17 are output units.

  FIG. 2 is a diagram illustrating the traveling direction of the image processing apparatus 10 according to the first embodiment. The left view of FIG. 2 and the right view of FIG. 2 are views seen from directions orthogonal to each other. Referring to the left diagram of FIG. 2, the image processing apparatus 10 moves in parallel with the extending direction of the shelf 20 as the mobile body 11 travels. Therefore, the photographing unit 13 can sequentially photograph each label attached to a plurality of articles placed on the shelf 20 while moving in parallel with the extending direction of the shelf 20.

  2, the image processing apparatus 10 stops moving in a direction parallel to the extending direction of the shelf 20 and moves in a direction orthogonal to the extending direction of the shelf 20 by the traveling of the moving body 11. To do. The image processing apparatus 10 moves in the direction orthogonal to the extending direction of the shelf 20 because the distance between the imaging unit 13 and the imaging target (the shelf 20, more specifically, the article placed on the shelf 20) is appropriate. This is to keep it in good condition. In addition, the distance between the imaging unit 13 and the imaging target is paraphrased as the distance between the moving body 11 and the shelf 20. Therefore, the image processing apparatus 10 can maintain the sharpness of the binary image area included in each image that the imaging unit 13 sequentially captures.

  Next, an index used for sharpness determination will be described. FIG. 3 is a diagram for explaining an example index used for the sharpness determination according to the first embodiment. FIG. 3 shows data relating to three different binary images. Each of the three images is a binary image region. The data indicated by “1” in FIG. 3 corresponds to the first image in focus. The first image is a clear image. The data indicated by “2” in FIG. 3 corresponds to the second image that is slightly out of focus than the first image. The second image is an image that is unclearer than the first image. Data corresponding to “3” in FIG. 3 corresponds to a third image that is further out of focus than the second image. The third image is an image that is further blurred than the second image.

  The left diagram of FIG. 3 is a graph representing data of an arbitrary one line of each of the first image, the second image, and the third image as an input function. The horizontal axis indicates the coordinates of each pixel included in one arbitrary line of one image, and the vertical axis indicates the gradation (pixel value). The processing unit 14 generates an input function from data of one image that is a target of sharpness determination. Note that one arbitrary line may correspond to the horizontal axis of the entire image or may correspond to the vertical axis.

  The central view of FIG. 3 is a graph representing the histograms of the first image, the second image, and the third image. The horizontal axis indicates gradation and the vertical axis indicates the number of pixels. The histogram is a distribution of pixels included in an arbitrary line of one image that is a target of sharpness determination, and is gradation information of pixels that form the image. The processing unit 14 generates a histogram from the input function. The two peaks of the histogram become sharper as the binary image becomes sharper. Further, the positions of the two peaks of the histogram are separated as the binary image becomes clearer.

  The right diagram of FIG. 3 is a graph showing the ratio (σ / S) (hereinafter referred to as SER) of the standard deviation σ and entropy S in each of the first image, the second image, and the third image. The processing unit 14 calculates the standard deviation σ and the entropy S based on the histogram using the following calculation formula. Thereafter, the processing unit 14 calculates the SER based on the standard deviation σ and the entropy S.

The formula for calculating the standard deviation σ is as follows.
here,
The formula for entropy S is as follows.
Here, n _i is the number of pixels of gradation i in the histogram, and n is the total number of pixels in the histogram.

  The standard deviation σ is an index representing the degree of separation of at least two peaks in the histogram. Entropy S is an index representing the sharpness of a peak in a histogram. SER is an index that quantitatively represents the sharpness of the binary image region. The standard deviation σ increases as the two peaks of the histogram move away. Entropy S decreases as the two peaks of the histogram become sharper. If the standard deviation σ is large and the entropy S is small, the value of SER is large.

  Referring to the right diagram of FIG. 3, the SER is larger in the order of the third image, the second image, and the first image. This order matches the order of images in which the degree of defocus is reduced. If the SER is large, it can be said that the binary image region is clear. Therefore, SER is effective as an index that quantitatively represents the sharpness of the binary image region.

  The SER may be a ratio of an index (an example is standard deviation σ) indicating the degree of separation of at least two peaks in the histogram and an index (an example is entropy S) indicating the sharpness of the peak in the histogram. Therefore, the processing unit 14 may calculate the SER using an index other than the standard deviation σ and the entropy S. For example, the standard deviation σ varies depending on the brightness of the entire image. Therefore, it is preferable that the processing unit 14 calculates the SER using a variation coefficient obtained by dividing the standard deviation σ by the average value m instead of the standard deviation σ. The processing unit 14 may calculate the SER using a variance that is the square of the standard deviation σ instead of the standard deviation σ. When calculating the entropy S, the processing unit 14 divides the number of pixels ni of each gradation by the total number of pixels n, but the number of pixels ni of each gradation may not be divided by the total number of pixels n.

  The SER is not limited to a value calculated based on any one line of one image. For example, the SER may be an average value of a plurality of SERs calculated from an arbitrary plurality of lines or all lines of one image.

  Next, the difference in SER between different images will be described. FIG. 4 is a diagram illustrating the SER calculated by the processing unit 14 according to the first embodiment. FIG. 4 shows three different images showing the same character string ABCD, respective histograms, and respective SERs.

  The left diagram of FIG. 4 shows a fourth image that is in focus. The fourth image is a clear binary image. The entire fourth image is a binary image region. The central view of FIG. 4 shows a fifth image that is more out of focus than the fourth image. The fifth image is a binary image that is less sharp than the fourth image. The entire fifth image is a binary image region. The right view of FIG. 4 shows a sixth image that is more in focus than the fourth image but is more in focus than the fifth image. The sixth image is clearer than the fourth image, but is clearer than the fifth image. However, the sixth image is an image having a smaller contrast than the fourth image throughout.

  As described above with reference to FIG. 3, the processing unit 14 can calculate the standard deviation σ, entropy S, and SER of the fourth image, the fifth image, and the sixth image, respectively.

  As shown in the left diagram of FIG. 4, the standard deviation σ of the fourth image is 82, the entropy S is 0.6, and the SER is 68. As shown in the center diagram of FIG. 4, the standard deviation σ of the fifth image is 71, the entropy S is 1.1, and the SER is 31. As shown in the right diagram of FIG. 4, the standard deviation σ of the sixth image is 31, the entropy S is 0.5, and the SER is 29.

  The SER of the fourth image is more than twice the SER of the fifth image. This is because the difference in entropy S between the two images is effective. On the other hand, the SER of the sixth image is about ½ of the SER of the fourth image. This is because the difference between the standard deviations σ of the two images is effective.

  The processing unit 14 can determine whether or not the binary image area included in the image is clear by comparing the SER and the reference value. If the SER is larger than the reference value, the processing unit 14 determines that the binary image area is clear. On the other hand, if the SER is not larger than the reference value, the processing unit 14 determines that the binary image area is not clear or the contrast of the image itself is small. Thus, SER is not only an index that can evaluate the sharpness state of the binary image area, but also an index that can simultaneously evaluate the contrast state of the image itself. Therefore, SER is effective as an index that quantitatively represents the sharpness of the binary image region.

  Next, an example of processing by the image processing apparatus 10 will be described. FIG. 5 is a flowchart of an example process performed by the image processing apparatus 10 according to the first embodiment.

  The moving body 11 starts traveling based on the control by the control unit 12 (Act 1001). The moving body 11 travels along a direction parallel to the extending direction of the shelf 20. The imaging unit 13 captures an image while moving an article (photographing target) placed on the shelf 20 (Act 1002). The processing unit 14 captures an image photographed by the photographing unit 13 (Act 1003). In Act 1003, the image captured from the photographing unit 13 to the processing unit 14 is an image that is a target of sharpness determination. The processing unit 14 calculates the standard deviation σ and the entropy S based on the entropy of the image that is the object of the sharpness determination, and calculates the SER based on the standard deviation σ and the entropy S (Act 1004). Act 1004 is performed by, for example, the calculation unit 141 in the processing unit 14.

  The processing unit 14 compares the SER with the first threshold (Act 1005). Act 1005 is performed by, for example, the comparison determination unit 142 in the processing unit 14. The first threshold corresponds to the first reference value stored in the storage unit 15. The first reference value is a reference for determining whether or not the binary image area included in the image is clear. An arbitrary value can be set in advance as the first reference value. For example, the first reference value may correspond to the SER of an image including a clear binary image area that has been captured in advance. The case where the SER is not larger than the first threshold means that the binary image area is not clear or the image itself does not include the binary image area. On the other hand, the case where SER is larger than the first threshold means that the binary image region is clear.

  When the SER is not larger than the first threshold (Act 1005, No), the control unit 12 controls the traveling of the moving body 11 to stop based on the signal from the processing unit 14 (Act 1006). The control unit 12 controls to stop the traveling of the moving body 11 based on a stop command from the processing unit 14. Note that the control unit 12 may determine whether the traveling of the moving body 11 is stopped based on the comparison result between the SER sent from the processing unit 14 and the first threshold value.

  In Act 1005, when the processing unit 14 determines that the SER is not greater than the first threshold, the processing unit 14 displays the comparison result between the SER and the first threshold at least one of the display unit 16 and the audio output unit 17. You can send it to one. The display unit 16 and the audio output unit 17 output a comparison result by the processing unit 14. The display unit 16 can display the comparison result by the processing unit 14. The voice output unit 17 can output the comparison result by the processing unit 14 by voice. As an example, the comparison result is the SER and the first threshold value. As another example, the comparison result is a warning that the binary image area is not clear or the photographing unit 13 is out of focus. By the output from the display unit 16 or the audio output unit 17, the administrator can recognize the state of the binary image area included in the image captured by the imaging unit 13.

  Next, the control unit 12 performs control so as to correct the distance between the imaging unit 13 and the subject to be captured in the current image based on the comparison result (Act 1007). In Act 1007, the control unit 12 controls the position of the moving body 11 so that the photographing unit 15 is focused. For example, the control unit 12 controls the mobile body 11 to travel a predetermined distance in a direction in which the distance between the mobile body 11 and the shelf 20 is reduced or released. The object to be photographed is a shelf 20, more specifically, an article placed on the shelf 20. The travel distance of the mobile body 11 can be set arbitrarily. Returning to Act 1002, the imaging unit 13 captures the same imaging target again. In other words, the image processing apparatus 10 processes a plurality of images in which the same shooting target is captured using Act 1002 to Act 1007 until the SER of the image in which the same shooting target is captured is greater than the first threshold.

  If the SER is larger than the first threshold (Act 1005, Yes), the processing unit 14 stores the current image that is the target of the sharpness determination in the storage unit 15 (Act 1008). Returning to Act 1001, the moving body 11 starts traveling. The image processing apparatus 10 determines the sharpness of a binary image area included in an image in which the next shooting target is captured.

  According to the processing shown in FIG. 5, the image processing apparatus 10 can quantitatively determine the sharpness of the binary image region included in the image by using SER. For this reason, the image processing apparatus 10 can sequentially store clear images in which different shooting targets are captured while appropriately maintaining the distance between the moving body 11 and the shelf 20.

  Next, another example of processing by the image processing apparatus 10 will be described. FIG. 6 is a flowchart of another example process performed by the image processing apparatus 10 according to the first embodiment.

  Since Act 2001 to Act 2004 and Act 2006 to Act 2008 in FIG. 6 are the same as Act 1001 to Act 1004 and Act 1006 to Act 1008, description thereof will be omitted.

  In Act 2005, the processing unit 14 determines whether or not the SER of the current image that is the target of the sharpness determination is maximum. Act 2005 is performed by, for example, the comparison determination unit 142 in the processing unit 14. Here, the processing by the processing unit 14 in Act 2005 will be described on the assumption that the image that is the target of the sharpness determination is an image in which the photographing target X is captured.

  In Act 2005, the processing unit 14 determines whether or not the SER of the first image in which the shooting target X is captured is maximum. However, at this time, the second threshold value to be compared with the SER of the first image is not stored in the storage unit 15. Therefore, the processing unit 14 stores the SER of the first image in the storage unit 15 as the second reference value. That is, the second reference value corresponds to the SER of the past image in which the same shooting target X as the current image is captured. The second threshold corresponds to the second reference value stored in the storage unit 15.

  Thereafter, in Act 2005 after Act 2006, Act 2007, and Act 2002 to Act 2004, the processing unit 14 determines whether or not the SER of the second image in which the imaging target X is captured is maximum. The second image is the current image that is the object of sharpness determination. The processing unit 14 compares the SER of the second image with the second threshold value. When the SER of the second image is not larger than the second threshold, the processing unit 14 determines that the SER corresponding to the second threshold is maximal. That is, the processing unit 14 determines that it has found an image in which the photographing target X having the maximum SER is shown. In Act 2008, the processing unit 14 stores in the storage unit 15 an image that is a basis for calculating the SER corresponding to the second threshold value. That is, it can be said that the binary image area of this image is clear.

  When the SER of the second image is larger than the second threshold, the processing unit 14 determines that the SER corresponding to the second threshold is not maximal. In other words, the processing unit 14 determines that an image in which the imaging target X that maximizes the SER has not yet been found. The processing unit 14 updates the second reference value based on the SER of the second image and stores it in the storage unit 15.

  Thereafter, in Act 2005 after Act 2006, Act 2007, and Act 2002 to Act 2004 again, the processing unit 14 determines whether or not the SER of the third image in which the imaging target X is captured is maximum. That is, the image processing apparatus 10 continues to process different images in which the same photographing target X is captured until a SER that is not greater than the second threshold is found in Act 2005. As described above, in Act 2005, the processing unit 14 determines an image serving as a basis for calculating the maximum SER among a plurality of images in which the same shooting target is captured.

  If the processing unit 14 determines that the SER of the current image that is the target of the sharpness determination is not maximal in Act 1005, as described with reference to FIG. 6, the display unit 16 and the audio output unit 17 The comparison result by the unit 14 may be output. As an example, the comparison results are SER and a second threshold. As another example, the comparison result is a warning such that the sharpness of the binary image region is not maximal or the photographing unit 13 is out of focus.

  According to the process shown in FIG. 6, the image processing apparatus 10 can obtain an image having a higher definition of the binary image area than the image obtained by the process shown in FIG. 5.

(Second Embodiment)
A second embodiment will be described. Here, parts that are different from the first embodiment will be described, and description of parts that are the same as those of the first embodiment will be omitted.

    FIG. 7 is a diagram illustrating an image serving as a comparative example. FIG. 7 shows two different images showing the same character string ABCD, respective histograms, and respective SERs. The left figure of FIG. 7 shows the seventh image in focus. The seventh image is a clear image. The right diagram in FIG. 7 shows an eighth image that is more out of focus than the seventh image. The seventh image and the eighth image are images in which the natural image region surrounds the binary image region. As shown in the left diagram of FIG. 7, the SER of the seventh image is 12. As shown in the right diagram in FIG. 7, the SER of the eighth image is 8. There is not enough difference between the SER of the seventh image in focus and the SER of the eighth image in focus. Therefore, it may be difficult for the image processing apparatus 10 to determine the sharpness of the binary image region included in this image only by calculating one SER from one image that is the target of the sharpness determination. Therefore, the image processing apparatus 10 according to the second embodiment divides one image, which is an object of sharpness determination, into a plurality of blocks as described below, and calculates the SER of each block.

  FIG. 8 is a diagram for explaining a sharpness determination method by the processing unit 14 according to the second embodiment. The upper diagram in FIG. 8 shows two different images in which the character strings ABCD identical to those in FIG. 7 are copied.

  The upper left figure of FIG. 8 shows a ninth image that is in focus. The ninth image is a clear image. The upper right diagram in FIG. 8 shows a tenth image that is less in focus than the ninth image. The tenth image is an image that is unclearer than the ninth image. The ninth image and the tenth image are images in which the natural image region surrounds the binary image region.

  In the second embodiment, the processing unit 14 divides one image that is a target of sharpness determination into a plurality of blocks, and calculates the SER of each block. Referring to the upper diagram in FIG. 8, the processing unit 14 divides the ninth image and the tenth image into 64 blocks. The processing unit 14 calculates the SER of each block, as described in the first embodiment, based on arbitrary one line data for each block. Note that one arbitrary line may correspond to the horizontal axis or the vertical axis of each block. In addition, the SER of each block may be an average value of a plurality of SERs calculated from an arbitrary plurality of lines or all lines of each block. Note that the number of image divisions can be arbitrarily set.

  The middle left diagram of FIG. 8 is a diagram in which histograms are arranged at positions corresponding to the respective blocks of the ninth image. The lower left diagram of FIG. 8 is a diagram in which SER values are arranged at positions corresponding to the blocks of the ninth image. In the ninth image, the SER of the block corresponding to the binary image region is 40 or more.

  8 is a diagram in which histograms are arranged at positions corresponding to the respective blocks of the tenth image. The lower right diagram in FIG. 8 is a diagram in which SER values are arranged at positions corresponding to the respective blocks of the tenth image. In the tenth image, the SER of the block corresponding to the binary image region is 20 or less. In the block corresponding to the binary image area, unlike the example shown in FIG. 7, the difference between the SER of the focused image and the SER of the unfocused image is large. Therefore, even if it is difficult for the image processing apparatus 10 to determine the sharpness of the binary image region based on one SER calculated from one image that is the target of the sharpness determination, the image processing device 10 determines whether the image processing device 10 uses each block of this image. The sharpness of the binary image region can be sufficiently determined based on each calculated SER.

  The processing unit 14 determines whether or not the binary image area included in the image is clear by comparing the SER of each block with a reference value. If the SER of the block is larger than the reference value, the processing unit 14 determines that the binary image area included in the block is clear. On the other hand, if the SER of the block is not larger than the reference value, the processing unit 14 determines that the binary image area included in this block is not clear. SER is effective as an index that quantitatively represents the sharpness of a binary image region even in an image in which a natural image region and a binary image region are mixed.

  Next, an example of processing by the image processing apparatus 10 will be described. FIG. 9 is a flowchart of an example process performed by the image processing apparatus 10 according to the second embodiment.

  The moving body 11 starts traveling based on the control by the control unit 12 (Act 3001). The moving body 11 travels along a direction parallel to the extending direction of the shelf 20. The imaging unit 13 performs imaging while moving an object (photographing target) placed on the shelf 20 (Act 3002). The processing unit 14 captures an image photographed by the photographing unit 13 (Act 3003). In Act 3003, the image captured from the photographing unit 13 to the processing unit 14 is an image that is a target of sharpness determination.

  The processing unit 14 divides this image into a plurality of blocks (Act 3004). The processing unit 14 calculates the standard deviation σ and entropy S of each block based on the entropy of each block in the plurality of blocks, and calculates the SER of each block based on the standard deviation σ and entropy S (Act 3005). Act 3005 is performed by, for example, the calculation unit 141 in the processing unit 14.

  The processing unit 14 acquires the number of OK blocks based on the value of each SER (Act 3006). The OK block corresponds to a block including a clear binary image area. In Act 3006, the processing unit 14 acquires the number of OK blocks as follows as an example. The processing unit 14 compares the SER of each block with the third threshold value. The third threshold value corresponds to the third reference value stored in the storage unit 15. The third reference value is a reference for determining whether or not the binary image area included in each block is clear. The third reference value can be arbitrarily set in advance. For example, the third reference value may correspond to the SER value of an image including a clear binary image area that has been captured in advance. The case where the SER of the block is not larger than the third threshold means that the binary image area included in the block is not clear or that the binary image area is not included in the block itself. means. On the other hand, the case where the SER of the block is larger than the third threshold means that the binary image area included in this block is clear.

  When the SER of an arbitrary block is larger than the third threshold value, the processing unit 14 determines that this block is an OK block. On the other hand, when the SER of an arbitrary block is not greater than the third threshold, the processing unit 14 determines that this block is not an OK block. The processing unit 14 compares the SER of all blocks constituting the image that is the target of the sharpness determination with the third threshold value. The processing unit 14 acquires the number of OK blocks in all the blocks constituting the image that is the object of sharpness determination. Here, a value obtained by dividing the number of OK blocks in the image that is the object of the sharpness determination by the number of all blocks constituting the image is referred to as a first ratio.

  The processing unit 14 compares the first ratio with the fourth threshold value (Act 3007). The fourth reference value is a reference for determining whether or not the binary image area included in the image is clear. The fourth reference value can be arbitrarily set in advance. As an example, the fourth reference value may be a value obtained by dividing the number of OK blocks in an image including a clear binary image area captured in advance by the number of all blocks constituting the image.

  Note that the case where the first ratio is not greater than the first threshold means that the binary image area included in the image is not clear or the image itself does not include the binary image area. To do. On the other hand, the case where the first ratio is larger than the first threshold means that the binary image area included in the image is clear.

  When the first ratio is not larger than the fourth threshold (Act 3007, No), the control unit 12 controls to stop the traveling of the moving body 11 based on the signal from the processing unit 14 (Act 3008). In Act 3008, the image processing apparatus 10 may perform the same processing as Act 1006 described above. When the processing unit 14 determines that the first ratio is not greater than the fourth threshold value in Act 3007, the display unit 16 and the audio output unit 17 output the comparison result as described with reference to FIG. May be. As an example, the comparison result is a first ratio and a fourth threshold value. As another example, the comparison result is a warning that the binary image area is not clear or the photographing unit 13 is out of focus.

  Next, the control unit 12 performs control to correct the position of the moving body 11 so that the photographing unit 15 is focused (Act 3009). In Act 3009, the image processing apparatus 10 may perform the same processing as Act 1007 described above. Returning to Act 3002, the imaging unit 13 captures the same imaging object again. In other words, the image processing apparatus 10 processes a plurality of images in which the same shooting target is captured using Act 3002 to Act 3009 until the first ratio in the image in which the same shooting target is captured is greater than the fourth threshold value.

  When the first ratio is greater than the fourth threshold (Act 3007, Yes), the processing unit 14 stores the current image that is the target of the sharpness determination in the storage unit 15 (Act 3010). Returning to Act 3001, the moving body 11 starts traveling. The image processing apparatus 10 determines the sharpness of a binary image area included in an image in which the next shooting target is captured.

  Next, another example of processing by the image processing apparatus 10 will be described. FIG. 10 is a flowchart of another example of processing performed by the image processing apparatus 10 according to the second embodiment.

  Act 4001 to Act 4006 and Act 4008 to Act 4010 in FIG. 10 are the same as Act 3001 to Act 3006 and Act 3008 to Act 3010 in FIG.

  In Act 4007, the processing unit 14 determines whether or not the first ratio of the current image that is the object of sharpness determination is a maximum. Act 4007 is performed by the comparison determination unit 142 in the processing unit 14. Here, the processing by the processing unit 14 in Act 4007 will be described on the assumption that the image that is the target of the sharpness determination is an image in which the shooting target Y is captured.

  In Act 4007, the processing unit 14 determines whether or not the first ratio of the first image in which the shooting target Y is captured is maximum. However, at this time, the fifth threshold value to be compared with the first ratio of the first image is not stored in the storage unit 15. Therefore, the processing unit 14 stores the first ratio of the first image in the storage unit 15 as the fifth reference value. That is, the fifth reference value corresponds to the first ratio of past images in which the same shooting target Y as the current image is captured. The fifth threshold corresponds to the fifth reference value stored in the storage unit 15.

  Thereafter, in Act 4007 after Act 4008, Act 4009, and Act 4002 to Act 4006, the processing unit 14 determines whether or not the first ratio of the second image in which the imaging target Y is captured is maximum. The second image is the current image that is the object of sharpness determination. The processing unit 14 compares the first ratio of the second image with the fifth threshold value. When the first ratio of the second image is not greater than the fifth threshold, the processing unit 14 determines that the first ratio corresponding to the fifth threshold is maximal. That is, the processing unit 14 determines that an image in which the photographing target Y having the maximum first ratio is found has been found. In Act 4010, the processing unit 14 stores the image that is the basis of the calculation of the first ratio corresponding to the fifth threshold in the storage unit 15. That is, it can be said that the binary image area of this image is clear.

  When the first ratio of the second image is larger than the fifth threshold, the processing unit 14 determines that the first ratio corresponding to the fifth threshold is not maximal. That is, the processing unit 14 determines that an image in which the imaging target Y having the maximum first ratio is not yet found. The processing unit 14 updates the fifth reference value based on the first ratio of the second image and stores it in the storage unit 15.

  Thereafter, in Act 4007 that has undergone Act 4008, Act 4009, and Act 4002 to Act 4006 again, the processing unit 14 determines whether or not the first ratio of the third image in which the imaging target Y is captured is maximum. That is, the image processing apparatus 10 continues to process different images in which the same shooting target Y is captured until a first ratio that is not greater than the fifth threshold is found in Act 4007. As described above, in Act 4007, the processing unit 14 determines an image serving as a basis for calculating the maximum first ratio among a plurality of images in which the same subject is captured.

  Note that when the processing unit 14 determines that the first ratio of the current image that is the target of the sharpness determination is not maximal in Act 4007, as described with reference to FIG. 5, the display unit 16 and the audio output unit 17 May output the comparison result. As an example, the comparison result is a first ratio and a fifth threshold. As another example, the comparison result is a warning such that the sharpness of the binary image region is not maximal or the photographing unit 13 is out of focus.

  The image processing apparatus 10 according to the second embodiment is more accurate than the image processing apparatus 10 according to the first embodiment in the sharpness of the binary image area in an image in which a natural image area and a binary image area are mixed. Can be determined.

(Third embodiment)
A third embodiment will be described. FIG. 11 is a block diagram of an image processing apparatus 10 as an example according to the third embodiment. The same components as those in the first embodiment are denoted by the same reference numerals, and the description thereof is omitted.

  The photographing unit 13 according to the third embodiment is a camera having an autofocus function and a focus determination function. The imaging unit 13 corrects the focus based on the signal from the processing unit 14.

  Next, description will be made again using FIGS. 5, 6, 9, and 10 for explaining an example of processing by the image processing apparatus 10 according to the third embodiment. In Act 1007 in FIG. 5, Act 2007 in FIG. 6, Act 3009 in FIG. 9, and Act 4009 in FIG. 10, the image processing 10 according to the third embodiment performs processing different from the first embodiment and the second embodiment.

  In Act 1007 in FIG. 5, Act 2007 in FIG. 6, Act 3009 in FIG. 9, and Act 4009 in FIG. 10, the photographing unit 13 corrects the focus so that the photographing unit 13 is focused on the subject to be photographed based on the comparison result. The amount of focus correction can be set arbitrarily. Note that the imaging unit 13 may correct the focus based on the comparison result sent from the processing unit 14 or may correct the focus based on the focus correction amount information sent from the processing unit 14.

  After Act 1007 in FIG. 5, Act 2007 in FIG. 6, Act 3009 in FIG. 9, and Act 4009 in FIG. 10, the imaging unit 13 captures the same object again with the focus corrected.

  According to the third embodiment, the same effects as those of the first embodiment and the second embodiment can be obtained.

  An entity that performs an operation is an entity related to a computer, such as hardware, a complex of hardware and software, software, software being executed, and the like. For example, the subject that performs the operation is a process, processor, object, executable file, thread, program, and computer executed on the processor, but is not limited thereto. For example, an image processing apparatus or an application executed there may be a main body that executes an operation. A process or thread may perform multiple actors that perform operations. The subject that performs the operation may be in one image processing apparatus, or may be distributed to a plurality of image processing apparatuses.

  The functions described above may be recorded in advance in the apparatus, or similar functions may be downloaded from the network to the apparatus, or the same functions stored in a recording medium may be installed in the apparatus. Good. The recording medium may take any form as long as it can store a program and can be read by the apparatus, such as a disk ROM or a memory card. In addition, the function obtained by installing or downloading in advance may be realized in cooperation with an OS (operating system) inside the apparatus.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  DESCRIPTION OF SYMBOLS 10 ... Image processing apparatus, 11 ... Moving body, 12 ... Control part, 13 ... Imaging | photography part, 14 ... Processing part, 15 ... Memory | storage part, 16 ... Display part, 17 ... Audio | voice output part, 20 ... Shelf, 131 ... Lens, 141: arithmetic unit, 142: comparison / determination unit, 151: reference value.

Claims (7)

An arithmetic unit that calculates standard deviation and entropy based on gradation information of pixels constituting an image, and calculates a ratio between the standard deviation and the entropy;
A comparison / determination unit for comparing the ratio with a reference value;
An output unit for outputting a comparison result by the comparison determination unit;
An image processing apparatus comprising:   The image processing apparatus according to claim 1, further comprising a photographing unit that photographs the image.   The image processing apparatus according to claim 2, further comprising a moving body that moves the image processing apparatus. A control unit for controlling the operation of the moving body;
The image processing apparatus according to claim 3, wherein the control unit controls the moving body so as to correct a distance between the photographing unit and an object captured in the image based on the comparison result.   The image processing apparatus according to claim 1, wherein the arithmetic unit divides the image into a plurality of blocks and calculates the standard deviation and the entropy of each block.   The image processing apparatus according to claim 1, further comprising a storage unit that updates and stores the reference value based on the value of the ratio. Calculating standard deviation and entropy based on gradation information of pixels constituting the image;
Calculating a ratio between the standard deviation and the entropy;
Comparing the ratio to a reference value;
Outputting a comparison result between the ratio and a reference value;
The computer-readable storage medium which memorize | stored the program which makes a computer perform.